Add model card

README.md

@@ -0,0 +1,11 @@
+---
+license: mit
+library_name: transformers
+pipeline_tag: feature-extraction
+---
+
+# EvoLen: Evolution-Guided Tokenization for DNA Language Model
+
+This model is a BERT-based DNA language model pretrained with the EvoLen tokenizer, as described in the paper [EvoLen: Evolution-Guided Tokenization for DNA Language Model](https://huggingface.co/papers/2604.08698). EvoLen incorporates evolutionary information into tokenization to better preserve functional sequence patterns.
+
+The model is designed for feature extraction and can be used for downstream tasks such as regulatory element classification and variant effect prediction. For code, pretraining and fine-tuning pipelines, and additional details, please refer to the [GitHub repository](https://github.com/HN020719/EvoLen). Checkpoints and datasets are also hosted under the [EvoLenTokenizer organization](https://huggingface.co/EvoLenTokenizer).